List files in each layer of an image tarball created through `docker save`.

list_files_in_docker_layers.py

#! /usr/bin/env python3
# -*- coding: utf-8 -*-
# vim:fenc=utf-8
#
# Copyright © 2022 Pi-Yueh Chuang <pychuang@pm.me>
#
# Distributed under terms of the BSD 3-Clause license.

"""List files in each layer of an image tarball created through `docker save`.
"""
import argparse
import logging
import pathlib
import tarfile
import tempfile


def main(image, logger):
    """Main function.
    """

    with tarfile.open(image, "r") as fobj:
        member = fobj.next()
        while member is not None:

            if "layer.tar" not in member.name:
                member = fobj.next()
                continue

            logger.info(f"{member.name}")
            with tempfile.TemporaryDirectory() as tempdir:
                fobj.extract(member, tempdir)
                with tarfile.open(f"{tempdir}/{member.name}", "r") as subfobj:
                    submember = subfobj.next()
                    while submember is not None:
                        logger.info(f"\t{submember.name}")
                        submember = subfobj.next()
            logger.info("")

            member = fobj.next()


if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="List files in each layer of a Docker image (in *.tar.gz format)")
    parser.add_argument("image", metavar="IMAGE", action="store", type=pathlib.Path)
    parser.add_argument("logfile", metavar="LOGFILE", action="store", type=pathlib.Path)
    args = parser.parse_args()

    logger = logging.getLogger(__name__)
    logging.basicConfig(handlers=[logging.NullHandler()], format="%(message)s", level=logging.DEBUG)
    logger.addHandler(logging.StreamHandler())
    logger.addHandler(logging.FileHandler(args.logfile, "w", "utf-8"))

    main(args.image, logger)